Agentsecurity

Preview uses restricted access, a boundary test checks denied writes, and execution requires separate approval

Run the agent in shadow mode before it changes anything

An agent’s preview is useful only if the boundary prevents writes. Review the proposed actions, then test the permissions behind the preview.

A left-to-right flow showing approved scope, scope expansion, stop and request, human approval, and a run record entry

A new permission means a new approval

A Claude Code run that widens scope after a one-time approval is working under an authorization you never gave. A new permission should mean a stop, a request, and a logged human approval, not a footnote in the summary.

A diagram showing an AI agent connecting through an MCP server to business systems, with scope, credentials, approvals, logs, and stop rules as controls

Your MCP server is part of the security boundary

MCP servers are not harmless connectors once agents use them to reach tickets, data, APIs, deployment tools, or RAG systems. Treat them as part of the security boundary.

A diagram showing delivery and control loops meeting at one release decision for production AI agents

Production AI agents need two loops

A production AI agent rollout fails when engineering proves the patch and security has to reconstruct the authority later. Run the delivery loop and the control loop together.

A diagram showing one control record connecting Claude Code delivery evidence with enterprise AI agent authority evidence

One control record for Claude Code and enterprise agents

Claude Code teams need delivery evidence. Enterprise AI agent teams need authority evidence. One small control record can connect both without turning every agent run into a governance ceremony.

A diagram showing an AI agent workflow with a stop rule before human approval

Give the agent a stop rule before you give it autonomy

Claude Code and enterprise AI agents need more than permissions. Teams need explicit stop rules that tell the agent when to pause, collect evidence, and hand control back to a human.

A diagram showing an AI agent delegation policy from task contract to rollback

Before you buy the agent platform, write the delegation policy

AI agent platforms do not decide your risk appetite. Before teams wire Claude Code, MCP, RAG, workflow tools, and release automation into production work, they need a clear delegation policy.

A diagram showing an agent pull request control record from task contract to release gate

If the agent opens a PR, keep a control record

Agent generated pull requests need more than a clean diff. Teams need a control record that captures scope, tools, tests, review evidence, rollback, and owner approval.

A diagram showing Claude Code delivery controls and enterprise AI security controls sharing one agent budget

Treat the agent budget as a security budget

Claude Code teams already budget scope, tools, review time, and rollback effort. Security teams should treat that same budget as delegated authority, evidence, and risk ownership.

A production AI agent operating model connecting engineering delivery controls with security evidence controls

The agent rollout needs one operating model

Teams buying Claude Code or enterprise AI agent guidance do not need two disconnected playbooks. They need one operating model that connects delivery speed, delegated authority, evidence, rollback, and security review.